Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    academic discourse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Scalars
    -0.07
    uchi
    -0.06
    bagai
    -0.06
     incel
    -0.06
     здійсню
    -0.06
     Getting
    -0.06
    .He
    -0.06
     cosplay
    -0.06
     tahmin
    -0.06
    yum
    -0.06
    POSITIVE LOGITS
    Bit
    0.06
    SPI
    0.06
     mệnh
    0.06
    尊
    0.06
    FTP
    0.06
    _FORWARD
    0.06
     AUD
    0.06
     Vermont
    0.06
    طبي
    0.06
     ***↵
    0.06
    Act Density 0.168%

    No Known Activations